CN114416493A - Vehicle software operation abnormity detection method - Google Patents
Vehicle software operation abnormity detection method Download PDFInfo
- Publication number
- CN114416493A CN114416493A CN202210114636.3A CN202210114636A CN114416493A CN 114416493 A CN114416493 A CN 114416493A CN 202210114636 A CN202210114636 A CN 202210114636A CN 114416493 A CN114416493 A CN 114416493A
- Authority
- CN
- China
- Prior art keywords
- cpu occupancy
- input
- model
- perception fusion
- detection method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/302—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a software system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3024—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a central processing unit [CPU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
- G06F11/327—Alarm or error message display
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a vehicle software operation abnormity detection method, which mainly comprises the following three steps: determining input and detection indexes of a software module, establishing a prediction model for the input and detection indexes through an AI training model, and comparing the detection indexes in the software operation process; according to the input data of the perception fusion program CPU and the CPU occupancy rate of the perception fusion corresponding moment, the relation between the CPU occupancy rate and the input data of the perception fusion program is analyzed, the CPU occupancy rate is finally predicted by using the input data of the perception fusion program, and if the deviation between the actual operation output of the program and the result of the model prediction output is overlarge, the operation is judged to be abnormal.
Description
Technical Field
The invention belongs to the technical field of detection of running conditions of automobile software or software modules, and particularly relates to a method for detecting running abnormity of the automobile software.
Background
In the field of automatic driving of vehicles, the running conditions of software or software modules, such as indexes of cpu occupancy rate, stack utilization rate, key output variables and the like, are monitored in real time, and whether abnormal running exists or not is judged, so that the method has a very important function, can prevent abnormal running of the vehicles caused by abnormal running of the software, and greatly improves the running safety of the vehicles.
In the prior art, as disclosed in the patent application entitled "monitoring method for operating status of vehicle domain controller" in CN113176771A, the monitoring method includes monitoring occurrence of relevant important events and abnormal events, and caching event occurrence time and event information in a memory in a form of log. The microcontroller unit and the microprocessor unit are used as core chips of the domain controller, the microcontroller unit is used for processing software functions with preset requirements on real-time performance and/or safety performance, the microprocessor unit is used for processing software functions with preset requirements on calculation performance and/or communication performance, and the domain controller for the vehicle has the advantages of giving consideration to real-time performance, safety performance, calculation performance and communication performance based on reasonable allocation and redundant backup of the microcontroller unit and the microprocessor unit, meeting the requirements of different software functions on various performances in vehicle network management and effectively improving the experience effect of the vehicle.
However, the above description mostly monitors and records the overall operation condition of the domain controller, but does not detect a single software or a software module, and cannot judge whether the function of a certain software or a software module is abnormally operated, and more is an abnormal event log management, and the definition of the abnormal event is fuzzy; the method can not judge whether a certain software or a software module is in an abnormal operation state at a certain moment through a big data analysis method, can not prevent abnormal vehicle running caused by abnormal operation of the software or the software module, and can not find or eliminate safety risks caused by abnormal operation of the software in time.
Disclosure of Invention
In view of the above-mentioned deficiencies in the prior art, the present invention provides a method for detecting abnormal operation of vehicle software, which determines whether a certain software or software module is in an abnormal operation state at a certain moment by using a big data analysis method, and finds out abnormal vehicle driving caused by abnormal operation of the software or software module in time, thereby finding out or eliminating safety risks caused by abnormal operation of the software in time.
The technical scheme of the invention is realized as follows:
a vehicle software operation abnormity detection method is characterized by comprising the following steps:
1) analyzing input data and cpu occupancy rate of the perception fusion program from the blf file;
2) screening input data of the perception fusion programs, and finding out input values of all perception fusion programs corresponding to the CPU occupancy rate output moment;
3) predicting input data correspondence of perception fusion program under all conditions by classification method
Each item of CPU occupancy;
4) taking input data of a perception fusion program as a characteristic variable, and firstly standardizing the characteristic variable; at present, the method
5) Regularizing the CPU input items to remove items with small influence on the CPU occupancy rate;
6) the CPU input items are used as characteristic variables, the characteristic variables are subjected to two-dimensional transformation and are converted into pictures, data in the picture format are input into a scene prediction model MobileNet, the model is trained, and one-time training is considered to be completed when the model finally starts to converge; continuously inputting data in a picture format into the model, optimizing the model until the final classification accuracy of the model reaches a set index N, and terminating model training;
7) and in the model verification stage, the program and the model run simultaneously, the input of the perception fusion program is consistent with the input of the scene prediction model, and if the difference between the scene prediction model and the cpu occupancy rate sent by the actual controller is higher than a set value M, the abnormality is judged. Therefore, the invention judges whether a certain software or software module is in an abnormal operation state at a certain moment through the analysis method of big data, and finds the abnormal vehicle running caused by the abnormal operation of the software or software module in time, thereby finding or eliminating the safety risk existing due to the abnormal operation of the software in time.
Further: the classification method in step 3) sets the parameter d as the interval of the CPU occupancy rates, manually classifies the CPU occupancy rates into 100/d categories, classifies the input data correspondingly output into the corresponding CPU occupancy rate categories by using the input items of the perception fusion program as features, gradually reduces the parameter d according to the classification effect until the parameter d is reduced to 1, classifies the input items of the perception fusion program corresponding to the output items into each 1% of the CPU occupancy rates by the classification method, namely, each CPU occupancy rate corresponding to the input data of the perception fusion program under all conditions can be predicted, and the prediction of the CPU occupancy rates is realized by the classification method. Therefore, because the CPU occupancy rate and the program input items are indirectly related, a good effect cannot be obtained by using a general regression method, the regression problem needs to be converted into a classification problem, and the CPU occupancy rate is predicted by the classification method.
Further: the step 4) of normalizing the characteristic variables is standard characteristic scaling or maximum and minimum characteristic scaling.
Further: the N in the step 6) is 90 percent. The data N is set according to specific conditions, and is convenient to adjust according to different models.
Further: m in the step 7) is 10 percent. This data M is set on a case-by-case basis, and is easily adjusted according to different models.
Further: and storing or outputting and displaying the result of the abnormal judgment to the vehicle end. Facilitating subsequent playback or monitoring.
Further: the scene prediction model adopts a MobileNET lightweight classification network.
Further: the input data source of the perception fusion program is sensor data, and at least comprises target data and lane line data.
In summary, the invention has the following beneficial effects:
1. whether a certain software or software module is in an abnormal operation state at a certain moment is judged through a big data analysis method, and the abnormal vehicle running caused by the abnormal operation of the software or the software module is found in time, so that the safety risk caused by the abnormal operation of the software can be found or eliminated in time.
2. The method and the system can guide developers to locate the cause of the problem, and can play a role in warning abnormal operation of software and the like.
Drawings
FIG. 1 is a flowchart of the processing of the present embodiment;
FIG. 2 is a flowchart of a predictive model system according to the present embodiment;
fig. 3 is a verification flowchart in the present embodiment.
Detailed Description
The following detailed description of specific embodiments of the invention refers to the accompanying drawings.
The exception of the present invention: the method defines the abnormity in a scene simulation mode, and judges the abnormity if the abnormity exceeds or falls to a certain standard instead of simply giving a standard. A software functional module (here, we describe as a sensing module running in the MPU in the item L3) is different scenarios for different inputs, and the different scenarios correspond to different indexes, which may be the cpu occupancy rate of the input or the scenario or the characteristics of the length, curvature, etc. of a certain lane line; and if the detection index deviation is overlarge in a similar scene, the software is abnormal in operation.
And (3) prediction model: the prediction model adopts a MobileNET lightweight classification network, the invention takes a perception fusion program of L3 as an example, the input source of the perception fusion program is sensor data, and the sensor data at least comprises target data and lane line data; the detection target is the cpu occupancy rate of the side mpu in the controller of the perception fusion program. The invention selects the parameter of the cpu occupancy rate as the detection index.
Referring to fig. 1-3, the invention discloses a method for detecting abnormal operation of vehicle software, which comprises the following steps:
1. the input data and the detection index of the perception fusion program, namely the cpu occupancy rate, are analyzed from blf files (blf is a binary data file, which is a format for storing data messages by on-board data acquisition equipment, wherein the analyzed blf file contains the related data of the on-board controller during operation), namely can messages and ethernet intermediate variables;
2. screening input data of the perception fusion programs, and finding out input values of all perception fusion programs corresponding to the CPU occupancy rate output moment;
3. predicting the CPU occupancy rate corresponding to the input data of the perception fusion program under all conditions by a classification method; in the conventional regression prediction problem, the interpreted quantity is generally considered to be a predictable value, but in the project, the correlation between the CPU occupancy and the program input item is not direct or indirect, so that the good effect cannot be achieved by using the general regression method. In order to solve the problem, the regression problem needs to be converted into a classification problem, a parameter d is set as the interval of the CPU occupancy rates, the CPU occupancy rates are manually classified into 100/d types, the input items of the perception fusion program are used as characteristics, the input data which are correspondingly output are classified into the corresponding CPU occupancy rates, the parameter d is gradually reduced according to the classification effect, if the classification effect is ideal, the parameter d can be finally reduced to 1, then the input items of the perception fusion program corresponding to the output items are classified into each 1% of the CPU occupancy rates through a classification method, namely, each CPU occupancy rate corresponding to the input data of the perception fusion program under all conditions can be predicted, and the CPU occupancy rates are predicted through the classification method.
4. Taking input data of a perception fusion program as a characteristic variable, and firstly standardizing the characteristic variable; the current common scheme is standard feature scaling or maximum minimum feature scaling.
5. Regularizing CPU input items, and removing items with small influence on CPU occupancy rate; because there are many CPU entries, the CPU entries need to be regularized to remove entries that have less impact on CPU occupancy.
6. The CPU input items are used as characteristic variables, the characteristic variables are subjected to two-dimensional transformation and are converted into pictures, data in a picture format are input into a scene prediction model (a common model in the prior art, the input data are scene-related characteristic variables and are named as a scene prediction model), and the model is trained, and when the model finally starts to converge, the training is regarded as one-time training completion. And continuously inputting data into the model, optimizing the model until the final classification accuracy of the model reaches a set index N, such as 90% or more, and terminating the model training.
7. And in the scene prediction model verification stage, the program and the model run simultaneously, the input of the perception fusion program is consistent with the input of the scene prediction model, and if the difference between the CPU occupancy rates of the prediction model and the CPU occupancy rates sent by the actual controller is higher than a set value M, if the CPU occupancy rates are set to be 10%, 12% and the like, the judgment of abnormality is carried out. And storing or outputting and displaying the result of judging the abnormity to a vehicle end, and providing the result for developers to position the problems.
The invention provides a software running abnormity detection method, which is a software abnormity detection method based on big data; the method is summarized into three main steps: determining input and detection indexes of a software module, establishing a prediction model for the input and detection indexes through an AI training model, and comparing the detection indexes in the software operation process.
According to the method, the relation between the CPU occupancy rate and the input data of the perception fusion program is analyzed according to the input data of the perception fusion program CPU and the CPU occupancy rate of the moment corresponding to the perception fusion, the CPU occupancy rate of the perception fusion program is finally predicted by utilizing the input data of the perception fusion program, and if the deviation between the actual operation output of the program and the result of the model prediction output is overlarge, the operation is judged to be abnormal.
Finally, it should be noted that the above-mentioned examples of the present invention are only examples for illustrating the present invention, and are not intended to limit the embodiments of the present invention. Although the present invention has been described in detail with reference to preferred embodiments, it will be apparent to those skilled in the art that other variations and modifications can be made based on the above description. Not all embodiments are exhaustive. All obvious changes and modifications of the present invention are within the scope of the present invention.
Claims (9)
1. A vehicle software operation abnormity detection method is characterized by comprising the following steps:
1) analyzing input data and cpu occupancy rate of the perception fusion program from the blf file;
2) screening input data of the perception fusion programs, and finding out input values of all perception fusion programs corresponding to the CPU occupancy rate output moment;
3) predicting input data correspondence of perception fusion program under all conditions by classification method
Each item of CPU occupancy;
4) taking input data of a perception fusion program as a characteristic variable, and firstly standardizing the characteristic variable;
5) regularizing the CPU input items to remove items with small influence on the CPU occupancy rate;
6) the CPU input items are used as characteristic variables, the characteristic variables are subjected to two-dimensional transformation and are converted into pictures, data in the picture format are input into a scene prediction model MobileNet, the model is trained, and one-time training is considered to be completed when the model finally starts to converge; continuously inputting data in a picture format into the model, optimizing the model until the final model classification accuracy reaches a set index N, and terminating model training;
7) and in the model verification stage, the program and the model run simultaneously, the input of the perception fusion program is consistent with the input of the scene prediction model, and if the difference between the scene prediction model and the cpu occupancy rate sent by the actual controller is higher than a set value M, the abnormality is judged.
2. The vehicle software operation abnormality detection method according to claim 1, characterized in that: the classification method in step 3) sets the parameter d as the interval of the CPU occupancy rates, manually classifies the CPU occupancy rates into 100/d categories, classifies the input data correspondingly output into the corresponding CPU occupancy rate categories by using the input items of the perception fusion program as features, gradually reduces the parameter d according to the classification effect until the parameter d is reduced to 1, classifies the input items of the perception fusion program corresponding to the output items into each 1% of the CPU occupancy rates by the classification method, namely, each CPU occupancy rate corresponding to the input data of the perception fusion program under all conditions can be predicted, and the prediction of the CPU occupancy rates is realized by the classification method.
3. The vehicle software operation abnormality detection method according to claim 1, characterized in that: the step 4) of normalizing the characteristic variables is standard characteristic scaling or maximum and minimum characteristic scaling.
4. A vehicle software operation abnormality detection method according to any one of claims 1 to 3, characterized in that: the N in the step 6) is 90 percent.
5. A vehicle software operation abnormality detection method according to any one of claims 1 to 3, characterized in that: m in the step 7) is 10 percent.
6. The vehicle software operation abnormality detection method according to claim 4, characterized in that: and storing or outputting and displaying the result of the abnormal judgment to the vehicle end.
7. The vehicle software operation abnormality detection method according to claim 5, characterized in that: and storing or outputting and displaying the result of the abnormal judgment to the vehicle end.
8. A vehicle software operation abnormality detection method according to any one of claims 1 to 3, characterized in that: the scene prediction model adopts a MobileNET lightweight classification network.
9. The vehicle software operation abnormality detection method according to claim 8, characterized in that: the input data source of the perception fusion program is sensor data, and at least comprises target data and lane line data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210114636.3A CN114416493A (en) | 2022-01-30 | 2022-01-30 | Vehicle software operation abnormity detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210114636.3A CN114416493A (en) | 2022-01-30 | 2022-01-30 | Vehicle software operation abnormity detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114416493A true CN114416493A (en) | 2022-04-29 |
Family
ID=81279155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210114636.3A Pending CN114416493A (en) | 2022-01-30 | 2022-01-30 | Vehicle software operation abnormity detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114416493A (en) |
-
2022
- 2022-01-30 CN CN202210114636.3A patent/CN114416493A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7778715B2 (en) | Methods and systems for a prediction model | |
| WO2021077983A1 (en) | Elevator fault determination logic verification method and system and storage medium | |
| WO2021217637A1 (en) | Terminal policy configuration method and apparatus, and computer device and storage medium | |
| CA2433941A1 (en) | Adaptive modeling of changed states in predictive condition monitoring | |
| CN111191545A (en) | Real-time monitoring and analyzing system and method for driver behavior | |
| CN113807547A (en) | Vehicle fault early warning method and system, readable storage medium and computer equipment | |
| CN111123223A (en) | General development platform, management system and method for radar health management | |
| CN110083515A (en) | Quick judgment method, device and the storage medium of slow disk in distributed memory system | |
| CN111024147A (en) | Component mounting detection method and device based on CNNs, electronic equipment and storage medium | |
| CN117687884A (en) | Intelligent optimization method and system for operation and maintenance operation ticket of power grid dispatching automation master station | |
| CN116450137A (en) | System abnormality detection method and device, storage medium and electronic equipment | |
| CN115756922A (en) | Fault prediction diagnosis method and device, electronic equipment and storage medium | |
| CN115858794A (en) | Abnormal log data identification method for network operation safety monitoring | |
| KR20150080336A (en) | Decision system for error of car using the data analysis and method therefor | |
| CN113221457B (en) | Method, device, equipment and medium for determining vehicle maintenance information | |
| CN114416493A (en) | Vehicle software operation abnormity detection method | |
| CN113032239A (en) | Risk prompting method and device, electronic equipment and storage medium | |
| CN113888775A (en) | Vehicle early warning method, server, storage medium, vehicle early warning system and vehicle | |
| CN111523609A (en) | Vehicle data processing method and device, computer equipment and storage medium | |
| CN109249933B (en) | Driver acceleration intention identification method and device | |
| CN116432397A (en) | Rail transit fault early warning method based on data model | |
| CN114821985A (en) | Industrial early warning system and method based on artificial intelligence | |
| CN111339142A (en) | Data monitoring response method, computer readable storage medium and data driving platform | |
| CN112733151A (en) | Embedded equipment firmware analysis method, device, medium and electronic equipment | |
| CN115017014B (en) | Highway electromechanical monitoring system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |